paper-with-me

홈 › Papers

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

2026-04-12 · Hao Wang, Guozhi Wang, Han Xiao, Yufeng Zhou, Yue Pan, Jichao Wang, Ke Xu, Yafei Wen, Xiaohu Ruan, Xiaoxin Chen, Honggang Qi arxiv

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by providing dense token-level supervision from a privileged teacher that has access to ground-truth answers. However, such fixed privileged information cannot capture the diverse valid strategies in agent tasks, and naively combining OPSD with RL often leads to training collapse. To address these limitations, we introduce Skill-SD, a framework that turns the agent's own trajectories into dynamic training-only supervision. Completed trajectories are summarized into compact natural language skills that describe successful behaviors, mistakes, and workflows. These skills serve as dynamic privileged information conditioning only the teacher, while the student always acts under the plain task prompt and learns to internalize the guidance through distillation. To stabilize the training, we derive an importance-weighted reverse-KL loss to provide gradient-correct token-level distillation, and dynamically synchronize the teacher with the improving student. Experimental results on agentic benchmarks demonstrate that Skill-SD substantially outperforms the standard RL baseline, improving both vanilla GRPO (+14.0%/+10.9% on AppWorld/Sokoban) and vanilla OPD (+42.1%/+40.6%). Project page: https://k1xe.github.io/skill-sd/

📄 PDF Abstract BibTeX arXiv:2604.10674

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Skill-Conditioned Gated Self-Distillation for LLM Reasoning

2026-05-27 · Jiazhen Huang, Xiao Chen, Xiao Luo, Yong Dai 외 arxiv

On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Existing methods usually assume trusted PI, s…

Mathematical Reasoning

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation

2026-06-28 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yiwen Ma 외 arxiv

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. Thi…

Reinforcement Learning

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

2026-09-17 · Yan Yu, Zhengxi Lu, Yizhou Liu, Yichen Pan 외 hf

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with…

Reinforcement Learning

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

2026-06-25 · Shuo Yang, Jinyang Wu, Zhengxi Lu, Yuhao Shen 외 arxiv

Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermediate decisions should be reinforced or su…

Reinforcement Learning

Self-Distillation Enables Continual Learning

2026-01-27 · Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal arxiv

Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce fo…

Reinforcement LearningContinual Learning